Overview

Image captioning studies how to turn images into useful descriptions, from brief scene summaries to detailed accounts of objects, attributes, relations, and changes. Common approaches combine vision encoders with Transformer or large vision-language model decoders; retrieval, region grounding, and reinforcement learning can add context or encourage more complete, faithful captions. Models are tested on datasets such as MS COCO, Flickr30k, and NoCaps, as well as specialized medical, remote-sensing, and multilingual benchmarks, using both text-overlap metrics and human or question-answering evaluations. A central challenge is balancing detail and coverage against hallucination, while evaluation remains difficult because reference captions are incomplete and automatic metrics can miss visual errors.

Latest papers

CardsList

103 papers8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

  1. Report of the 8th LSVOS Challenge: Mobile Unified Multimodal Understanding

    Nov 12, 2026Chang Liu, Henghui Ding, Tong Yang +10Unified Multimodal ModelsMultimodal Model Evaluation

  2. Fine-Grained Generative Hallucination Detection and Correction for Aerial Image Captioning

    Nov 11, 2026Debolena Basak, Somsubhra De, Maunendra Sankar DesarkarHallucination Detection in VLMsVLM Hallucination Mitigation

  3. Multi-Node Transformers for Object Detection and Captioning Across Distributed Edge Networks

    Nov 8, 2026Saurabh Kumar, Dewant Katare, Prakriti JainObject DetectionImage Captioning

  4. GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description

    Nov 6, 2026Rochak Dhakal, Chen Zhao, Soup Cobb +3Image CaptioningSurgical Video Understanding

  5. BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression

    Nov 6, 2026Gonçalo Gomes, Bruno Martins, Chrysoula ZervaImage Captioning EvaluationUncertainty Calibration

  6. Describe Your Facial Expressions by Linking Image Encoders and Large Language Models

    Nov 5, 2026Yujian Yuan, Jiabei Zeng, Shiguang ShanImage CaptioningVision-Language Models

  7. Where Do Long Captions Fail? Position-Aware Diagnosis and Reinforcement Learning for Detailed Image Captioning

    Oct 22, 2026Yuanze Hu, Zhichao Yang, Junwei Jing +9Image CaptioningFaithfulness in VLMs

  8. Class-Grounded Batik Captioning under Scarce Text Annotation: Label Retention and Source-Specific Error Propagation

    Oct 22, 2026Novanto Yudistira, Muhammad Dzaka Aufa Fadhillah, Irawati Nurmala SariImage CaptioningImage Captioning Evaluation

  9. Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels

    Oct 12, 2026Ruilin Gong, Hao GongT2I GenerationImage Tokenization

  10. Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning

    Oct 10, 2026Thanh Nguyen, Hee Suk Yoon, Tung Minh Luu +2Object Hallucination in VLMsVLM Hallucination Mitigation

  11. Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT

    Oct 6, 2026Zhen Yu, Wenyang Liu, Kejun Wu +3Image CaptioningPrivacy-Preserving ML

  12. PAIQ: Patch-Aligned Semantic Injection via Residual Rotation

    Sep 29, 2026Pinze Ren, Yuwei Zhang, Hao Chen +3Visual Question AnsweringImage Captioning

  13. Momentum-Coupled Rubric Adaptation for Detailed Image Captioning

    Sep 29, 2026Zhenwen Ji, Lei Jin, Shanyong Wang +6Image CaptioningRubric-Based RL

  14. Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains

    Sep 20, 2026Kiran Naseer, Samreen Azhar, Dwarikanath MahapatraImage CaptioningVLM Adaptation

  15. Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint

    Sep 17, 2026Zhiyun Jiang, Hanyong Wang, Binbin Liang +3Image CaptioningVision-Language Models

  16. Efficient Unified Multimodal Understanding (EUMU): Winning Solution for the MUMU Track at the 8th LSVOS Challenge

    Sep 16, 2026Dayoung Kil, Seong-heum KimUnified Multimodal ModelsEfficient Multimodal Inference

  17. PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

    Sep 16, 2026Sara Pieri, Evangelos Kazakos, Shizhe Chen +2Image CaptioningPanoptic Segmentation

  18. RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes

    Sep 12, 2026Abhirama Subramanyam Penamakuri, Shreya Shukla, Anand MishraImage CaptioningRetrieval-Augmented Generation

  19. Human-Centric Image Captioning with Subject-Centered Spatial Understanding

    Sep 8, 2026Bozhou Li, Jiahang Zhang, Yue Ding +11VLM EvaluationImage Captioning

  20. Controllable Image Captioning with Prompt-Conditioned Scene Rewards

    Sep 1, 2026Jongyeop Hyun, Taeyoung Kim, Hyounghun KimImage CaptioningRL for VLMs

  21. ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs

    Sep 1, 2026Yuta Kato, Shintaro Ozaki, Kazuki Hayashi +4Retrieval-Augmented GenerationImage Captioning

  22. A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss

    Sep 1, 2026Suryaansh Jain, Rahasya Barkur, Vishal G +8Contrastive LearningImage Captioning

  23. An Integrated Vision-and-Language Pretraining (VLP) and Visual Question Answering (VQA) model to Automate Nondestructive Evaluation Image Analysis

    Aug 29, 2026Mehrdad Shafiei Dizaji, Hoda AzariNon-Destructive TestingImage Captioning

  24. Focus Where It Counts: A Salience-Driven Vision-Language Model for Low Vision Assistance

    Aug 28, 2026Jiazhao Liang, Hao Huang, Shuaihang Yuan +8Assistive Technology for Blind and Low-Vision PeopleImage Captioning

  25. LUX: A Lesion-Aware Graph-Conditioned Visual - Language Architecture for Explainable Endoscopic Captioning

    Aug 24, 2026Alexis Ivan Escamilla-Lopez, Gilberto Ochoa-Ruiz, Salvador Hinojosa +1Image CaptioningMedical VLMs

  26. PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models

    Aug 22, 2026Jihyung Ko, Eunji Jung, Hyeongsub Kim +4Image CaptioningVision-Language Models

  27. Re3^3Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning

    Aug 21, 2026Haonan Jia, Shichao Dong, Zenghui Sun +7Image CaptioningRL for VLMs